Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 159 148 404 361 489 714 537 934 505 127 584 401 678 423 386 390 544 428 133 552
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1]  NA 423 361 678 714 584 544 401 489 159 390 133 505 934  NA 127 537 148 552  NA 428 404 386
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 1 1 3 1 3 5 3 5 3 2
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "o" "b" "a" "v" "j" "R" "Q" "P" "K" "O"

Are all/any elements TRUE

  • Input: logical vector
  • Output: single logical value
  • Task: try, understand what happens when you use manyNumbersWithNA instead of manyNumbers.
all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 8
which( manyNumbersWithNA > 900 )
[1] 14
which( is.na( manyNumbersWithNA ) )
[1]  1 15 20

Filtering vector elements

  • Input: any vector and filtering condition
  • Output: elements of the input vector
  • Note: several ways to get the same effect
manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 934
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 934
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 934

Are some elements among other elements

  • Input: two vectors
  • Output: a logical vector corresponding to the first input vector
"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "R" "Q" "P" "K" "O"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "o" "b" "a" "v" "j"
manyNumbers %in% 300:600
 [1] FALSE FALSE  TRUE  TRUE  TRUE FALSE  TRUE FALSE  TRUE FALSE  TRUE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE
[18]  TRUE FALSE  TRUE
which( manyNumbers %in% 300:600 )
 [1]  3  4  5  7  9 11 12 14 15 16 17 18 20
sum( manyNumbers %in% 300:600 )
[1] 13

Pick one of two (three) depending on condition

  • Input: a logical vector and two vectors additional vectors (for TRUE, for FALSE)
  • Output: elements of the additional vectors
  • Note: it can take care of NAs
if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] NA      "small" "small" "large" "large" "large" "large" "small" "small" "small" "small" "small" "large"
[14] "large" NA      "small" "large" "small" "large" NA      "small" "small" "small"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "UNKNOWN" "small"   "small"   "large"   "large"   "large"   "large"   "small"   "small"   "small"  
[11] "small"   "small"   "large"   "large"   "UNKNOWN" "small"   "large"   "small"   "large"   "UNKNOWN"
[21] "small"   "small"   "small"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]  NA   0   0 678 714 584 544   0   0   0   0   0 505 934  NA   0 537   0 552  NA   0   0   0

Duplicates and unique elements

  • Input: a vector
unique( duplicatedNumbers )
[1] 1 3 5 2
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  1  3  5  2
duplicated( duplicatedNumbers )
 [1] FALSE  TRUE FALSE  TRUE  TRUE FALSE  TRUE  TRUE  TRUE FALSE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 14
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 934
which.min( manyNumbersWithNA )
[1] 16
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 127
range( manyNumbersWithNA, na.rm = TRUE )
[1] 127 934

Sorting/ordering of vectors

manyNumbersWithNA
 [1]  NA 423 361 678 714 584 544 401 489 159 390 133 505 934  NA 127 537 148 552  NA 428 404 386
sort( manyNumbersWithNA )
 [1] 127 133 148 159 361 386 390 401 404 423 428 489 505 537 544 552 584 678 714 934
sort( manyNumbersWithNA, na.last = TRUE )
 [1] 127 133 148 159 361 386 390 401 404 423 428 489 505 537 544 552 584 678 714 934  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 934 714 678 584 552 544 537 505 489 428 423 404 401 390 386 361 159 148 133 127  NA  NA  NA
manyNumbersWithNA[1:5]
[1]  NA 423 361 678 714
order( manyNumbersWithNA[1:5] )
[1] 3 2 4 5 1
rank( manyNumbersWithNA[1:5] )
[1] 5 2 1 3 4
sort( mixedLetters )
 [1] "a" "b" "j" "K" "o" "O" "P" "Q" "R" "v"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 10.0  4.0  6.0  4.0  1.5  1.5  8.0  4.0  8.0  8.0
rank( manyDuplicates, ties.method = "min" )
 [1] 10  3  6  3  1  1  7  3  7  7
rank( manyDuplicates, ties.method = "random" )
 [1] 10  3  6  4  1  2  7  5  8  9

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000 -1.3567544 -0.5357007 -1.9638927 -1.3536890
[10]  0.5531375  0.2536436  0.8945281 -1.1225877 -0.6856098 -0.1121617
round( v, 0 )
 [1] -1  0  0  0  1 -1 -1 -2 -1  1  0  1 -1 -1  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -1.4 -0.5 -2.0 -1.4  0.6  0.3  0.9 -1.1 -0.7 -0.1
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -1.36 -0.54 -1.96 -1.35  0.55  0.25  0.89 -1.12 -0.69 -0.11
floor( v )
 [1] -1 -1  0  0  1 -2 -1 -2 -2  0  0  0 -2 -1 -1
ceiling( v )
 [1] -1  0  0  1  1 -1  0 -1 -1  1  1  1 -1  0  0

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC